arXiv subjects

Keshuai Xu

Publications and source records attributed to Keshuai Xu.

3 recordsLinked to original sources

arXiv2025

An Effectiveness Study Across Baseline and Learning-based Force Estimation Methods on the da Vinci Research Kit Si System

Robot-assisted minimally invasive surgery, such as through the da Vinci systems, improves precision and patient outcomes. However, da Vinci systems prior to da Vinci 5, lacked direct force-sensing capabilities, forcing surgeons to operate without the haptic feedback they get through laparoscopy. Our prior work restored force sensing through machine learning-based force estimation for the da Vinci Research Kit (dVRK) Classic. This study extends our previous method to the newer dVRK system, the dVRK-Si. Additionally, we benchmark the performance of the learning-based algorithm against baseline methods (which make simplifying assumptions on the torque) to study how the two systems differ. Results show the learning-based method achieves an average root-mean-square-error (RMSE) of 5.21\%, for the dVRK-Si, which is comparable to the dVRK Classic. In both systems, the learning-based method outperforms baselines, but the difference is much larger in the dVRK-Si. Nonetheless, dVRK-Si force estimation accuracy lags behind the dVRK Classic, with RMSE 2 to 3 times higher. Further analysis reveals poor PID control in the dVRK-Si. We hypothesize that this is due to the lack of gravity compensation, as unlike the dVRK Classic, the dVRK-Si is not mechanically balanced. This study advances the understanding of learning-based force estimation and is the first work to characterize the dynamics of the new dVRK-Si system.

cs.RO↗

arXiv2022

Feature-aggregated spatiotemporal spine surface estimation for wearable patch ultrasound volumetric imaging

Clear identification of bone structures is crucial for ultrasound-guided lumbar interventions, but it can be challenging due to the complex shapes of the self-shadowing vertebra anatomy and the extensive background speckle noise from the surrounding soft tissue structures. Therefore, we propose to use a patch-like wearable ultrasound solution to capture the reflective bone surfaces from multiple imaging angles and create 3D bone representations for interventional guidance. In this work, we will present our method for estimating the vertebra bone surfaces by using a spatiotemporal U-Net architecture learning from the B-Mode image and aggregated feature maps of hand-crafted filters. The methods are evaluated on spine phantom image data collected by our proposed miniaturized wearable "patch" ultrasound device, and the results show that a significant improvement on baseline method can be achieved with promising accuracy. Equipped with this surface estimation framework, our wearable ultrasound system can potentially provide intuitive and accurate interventional guidance for clinicians in augmented reality setting.

eess.IV↗

arXiv2022

Insonification Angle-based Ultrasound Volume Reconstruction for Spine Intervention

Ultrasound-guided spine interventions, such as lumbar-puncture procedures, often suffer from the reduced visibility of key anatomical features such as the inter-spinous process space, due to the complex shape of the self-shadowing vertebra. Therefore, we propose to design a wearable 3D ultrasound device capable of imaging the vertebra from multiple insonification angles to improve the 3D bone surface visualization for interventional guidance. In this work, we aim to equip the imaging platform with a reconstruction algorithm taking advantage of the redundant ultrasound beam angles. Specifically, we try to weight each beam's contribution for the same reconstructed voxel during the reconstruction process based on its incidence angle to the estimated bone surface. To validate our approach, we acquired multi-angle ultrasound image data on a spine phantom with a tracked phased array transducer. The results show that with the proposed method the bone surface contrast can be significantly enhanced, providing clearer visual guidance for the clinician to perform spine intervention.

cs.GR↗